基于变权缓冲算子的灰色G(1,1)模型在地铁能耗预测中的应用

Application of Grey G(1,1) Model Based on Variable Weight Buffer Operator in Metro Energy Consumption Prediction

准确预测城市轨道交通系统能源消耗量对城市轨道交通建设规划、环境保护及节能减排具有重要意义.城市轨道交通系统能源消耗量逐年上升且呈指数型变化趋势,因而适合用灰色理论G(1,1)模型描述其变化规律.为了提高模型的预测精度,采用了变权缓冲算子对历史建模数据进行预处理.实例分析表明,经遗传算法权值优化的强化缓冲算子明显增强了建模数据的指数变化特征,提高了灰色G(1,1)模型的预测精度,使预测结果更贴近实际.

Accurate prediction of energy consumption in urban rail transit system is of great significance to urban rail transit construction planning,environmental protection and energy saving and emission reduction.The energy consumption of urban rail transit system is increasing year by year and exponentially changing trend,so it is suitable to describe the change rule with the grey theory G(1,1) model.In order to improve the prediction accuracy of the model,variable weight buffer operator is used to preprocess the historical modeling data.The example analysis shows that the enhanced buffering operator optimized by genetic algorithm significantly enhances the exponential variation characteristics of the modeling data,improves the prediction accuracy of the grey G(1,1) model,and makes the prediction results closer to reality.